© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14913
    Prev
    Next
    INDEX
    Explanations

    French words for numbers, body parts, and common articles/pronouns

    oai_token-act-pair · gemini-2.0-flash

    mixed languages and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.40
    دانشنامهٔ
    -0.38
    TypeDef
    -0.37
     TeV
    -0.37
     spacers
    -0.33
    /***/
    -0.33
     aseg
    -0.32
     tirantes
    -0.32
    förder
    -0.32
    Sooo
    -0.32
    POSITIVE LOGITS
     nakalista
    0.69
    lies
    0.69
    Portale
    0.67
     дописавши
    0.67
     Vitae
    0.66
    liament
    0.66
    unteer
    0.65
    Personendaten
    0.65
    uitton
    0.65
    OUGHT
    0.64
    Activations Density 0.231%

    No Known Activations